{"id":"https://openalex.org/W3043663496","doi":"https://doi.org/10.1109/iros45743.2020.9341557","title":"Look and Listen: A Multi-modality Late Fusion Approach to Scene Classification for Autonomous Machines","display_name":"Look and Listen: A Multi-modality Late Fusion Approach to Scene Classification for Autonomous Machines","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W3043663496","doi":"https://doi.org/10.1109/iros45743.2020.9341557","mag":"3043663496"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9341557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.10175","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080362193","display_name":"Jordan J. Bird","orcid":"https://orcid.org/0000-0002-9858-1231"},"institutions":[{"id":"https://openalex.org/I169199633","display_name":"Aston University","ror":"https://ror.org/05j0ve876","country_code":"GB","type":"education","lineage":["https://openalex.org/I169199633"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jordan J. Bird","raw_affiliation_strings":["Aston Robotics Vision and Intelligent Systems (ARVIS) Lab","School of Engineering and Applied Science, Aston University, Birmingham, United Kingdom","Aston University,School of Engineering and Applied Science,Birmingham,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aston Robotics Vision and Intelligent Systems (ARVIS) Lab","institution_ids":[]},{"raw_affiliation_string":"School of Engineering and Applied Science, Aston University, Birmingham, United Kingdom","institution_ids":["https://openalex.org/I169199633"]},{"raw_affiliation_string":"Aston University,School of Engineering and Applied Science,Birmingham,United Kingdom","institution_ids":["https://openalex.org/I169199633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032454100","display_name":"Diego R. Faria","orcid":"https://orcid.org/0000-0002-2771-1713"},"institutions":[{"id":"https://openalex.org/I169199633","display_name":"Aston University","ror":"https://ror.org/05j0ve876","country_code":"GB","type":"education","lineage":["https://openalex.org/I169199633"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Diego R. Faria","raw_affiliation_strings":["Aston Robotics Vision and Intelligent Systems (ARVIS) Lab","School of Engineering and Applied Science, Aston University, Birmingham, United Kingdom","Aston University,School of Engineering and Applied Science,Birmingham,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aston Robotics Vision and Intelligent Systems (ARVIS) Lab","institution_ids":[]},{"raw_affiliation_string":"School of Engineering and Applied Science, Aston University, Birmingham, United Kingdom","institution_ids":["https://openalex.org/I169199633"]},{"raw_affiliation_string":"Aston University,School of Engineering and Applied Science,Birmingham,United Kingdom","institution_ids":["https://openalex.org/I169199633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039508418","display_name":"Cristiano Premebida","orcid":"https://orcid.org/0000-0002-2168-2077"},"institutions":[{"id":"https://openalex.org/I4210125590","display_name":"Institute for Systems Engineering and Computers","ror":"https://ror.org/033wn8m60","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I76903346","display_name":"University of Coimbra","ror":"https://ror.org/04z8k9a98","country_code":"PT","type":"education","lineage":["https://openalex.org/I76903346"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Cristiano Premebida","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Institute of Systems and Robotics, University of Coimbra, Coimbra, Portugal","University of Coimbra, Institute of Systems and Robotics, Department of Electrical and Computer Engineering, Coimbra, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Institute of Systems and Robotics, University of Coimbra, Coimbra, Portugal","institution_ids":["https://openalex.org/I4210125590","https://openalex.org/I76903346"]},{"raw_affiliation_string":"University of Coimbra, Institute of Systems and Robotics, Department of Electrical and Computer Engineering, Coimbra, Portugal","institution_ids":["https://openalex.org/I4210125590","https://openalex.org/I76903346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076983719","display_name":"Anik\u00f3 Ek\u00e1rt","orcid":"https://orcid.org/0000-0001-6967-5397"},"institutions":[{"id":"https://openalex.org/I169199633","display_name":"Aston University","ror":"https://ror.org/05j0ve876","country_code":"GB","type":"education","lineage":["https://openalex.org/I169199633"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Aniko Ekart","raw_affiliation_strings":["School of Engineering and Applied Science, Aston University, Birmingham, United Kingdom","Aston University,School of Engineering and Applied Science,Birmingham,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering and Applied Science, Aston University, Birmingham, United Kingdom","institution_ids":["https://openalex.org/I169199633"]},{"raw_affiliation_string":"Aston University,School of Engineering and Applied Science,Birmingham,United Kingdom","institution_ids":["https://openalex.org/I169199633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020722131","display_name":"George Vogiatzis","orcid":"https://orcid.org/0000-0002-3226-0603"},"institutions":[{"id":"https://openalex.org/I169199633","display_name":"Aston University","ror":"https://ror.org/05j0ve876","country_code":"GB","type":"education","lineage":["https://openalex.org/I169199633"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"George Vogiatzis","raw_affiliation_strings":["Aston Robotics Vision and Intelligent Systems (ARVIS) Lab","School of Engineering and Applied Science, Aston University, Birmingham, United Kingdom","Aston University,School of Engineering and Applied Science,Birmingham,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aston Robotics Vision and Intelligent Systems (ARVIS) Lab","institution_ids":[]},{"raw_affiliation_string":"School of Engineering and Applied Science, Aston University, Birmingham, United Kingdom","institution_ids":["https://openalex.org/I169199633"]},{"raw_affiliation_string":"Aston University,School of Engineering and Applied Science,Birmingham,United Kingdom","institution_ids":["https://openalex.org/I169199633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10380","last_page":"10385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.753752589225769},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7122657895088196},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6725194454193115},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.626253604888916},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6140945553779602},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5566419959068298},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.46950364112854004}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.753752589225769},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7122657895088196},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6725194454193115},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.626253604888916},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6140945553779602},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5566419959068298},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.46950364112854004},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/iros45743.2020.9341557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.aston.ac.uk:43074","is_oa":false,"landing_page_url":"https://publications.aston.ac.uk/view/author/29662b19e235d25ecd752a109a3b4569.html>,","pdf_url":null,"source":{"id":"https://openalex.org/S4306400483","display_name":"Aston Publications Explorer (Aston University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169199633","host_organization_name":"Aston University","host_organization_lineage":["https://openalex.org/I169199633"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Book Section"},{"id":"pmh:oai:arXiv.org:2007.10175","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.10175","pdf_url":"https://arxiv.org/pdf/2007.10175","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3043663496","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2007.10175","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:irep.ntu.ac.uk:48134","is_oa":false,"landing_page_url":"http://irep.ntu.ac.uk/id/eprint/48134/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400559","display_name":"Nottingham Trent University's Institutional Repository (Nottingham Trent Repository)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I52590639","host_organization_name":"Nottingham Trent University","host_organization_lineage":["https://openalex.org/I52590639"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Book Section"},{"id":"doi:10.48550/arxiv.2007.10175","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.10175","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.10175","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.10175","pdf_url":"https://arxiv.org/pdf/2007.10175","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3043663496.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1501067615","https://openalex.org/W1637570796","https://openalex.org/W1909234690","https://openalex.org/W1952323793","https://openalex.org/W1956982159","https://openalex.org/W2058189943","https://openalex.org/W2103869314","https://openalex.org/W2134670479","https://openalex.org/W2137097255","https://openalex.org/W2137561966","https://openalex.org/W2138502025","https://openalex.org/W2153811331","https://openalex.org/W2164587673","https://openalex.org/W2212106655","https://openalex.org/W2258484932","https://openalex.org/W2499439150","https://openalex.org/W2619697695","https://openalex.org/W2904848479","https://openalex.org/W2944314241","https://openalex.org/W2950664434","https://openalex.org/W2962835968","https://openalex.org/W2962888833","https://openalex.org/W2963190516","https://openalex.org/W3088601509","https://openalex.org/W3146177989","https://openalex.org/W6606244218","https://openalex.org/W6636885848","https://openalex.org/W6637373629","https://openalex.org/W6679792166"],"related_works":["https://openalex.org/W3130406858","https://openalex.org/W2605364946","https://openalex.org/W2949726975","https://openalex.org/W2949406885","https://openalex.org/W2900791537","https://openalex.org/W3142098745","https://openalex.org/W2990434713","https://openalex.org/W3128384204","https://openalex.org/W3095411711","https://openalex.org/W2774571176","https://openalex.org/W2945337168","https://openalex.org/W2955375852","https://openalex.org/W3174822832","https://openalex.org/W2540481276","https://openalex.org/W3114627802","https://openalex.org/W3105202226","https://openalex.org/W2788994472","https://openalex.org/W3043451948","https://openalex.org/W2786797739","https://openalex.org/W3175109429"],"abstract_inverted_index":{"The":[0,27,72,133],"novelty":[1],"of":[2,23,37,43,50,52,58,95,106,120],"this":[3,123],"study":[4],"consists":[5],"in":[6,20,122,187],"a":[7,21,32,83,113,163,184,188,192,200,206],"multi-modality":[8,124,222],"approach":[9,28],"to":[10,111,118],"scene":[11],"classification,":[12],"where":[13,162],"image":[14,73,210],"and":[15,40,65,74,86,97,130,199],"audio":[16,67,76,131,196],"complement":[17],"each":[18],"other":[19],"process":[22],"deep":[24,90],"late":[25,104,139],"fusion.":[26],"is":[29,101],"demonstrated":[30],"on":[31],"difficult":[33],"classification":[34],"problem,":[35],"consisting":[36],"two":[38,108,150],"synchronised":[39,127],"balanced":[41],"datasets":[42,77],"16,000":[44],"data":[45,170],"objects,":[46],"encompassing":[47],"4.4":[48],"hours":[49],"video":[51,63,128],"8":[53],"environments":[54],"with":[55,93,126],"varying":[56],"degrees":[57],"similarity.":[59],"We":[60,158],"first":[61,79],"extract":[62],"frames":[64,129],"accompanying":[66],"at":[68],"one":[69],"second":[70],"intervals.":[71],"the":[75,107,149,195,209],"are":[78,153,172,214,217],"classified":[80,219],"independently,":[81],"using":[82],"fine-tuned":[84],"VGG16":[85],"an":[87,176],"evolutionary":[88],"optimised":[89],"neural":[91,109,135],"network,":[92],"accuracies":[94],"89.27%":[96],"93.72%,":[98],"respectively.":[99],"This":[100],"followed":[102],"by":[103,145,168,194,208,220],"fusion":[105,140],"networks":[110,152],"enable":[112],"higher":[114,178],"order":[115,179],"function,":[116],"leading":[117],"accuracy":[119],"96.81%":[121],"classifier":[125,197,211],"clips.":[132],"tertiary":[134],"network":[136],"implemented":[137],"for":[138],"outperforms":[141],"classical":[142],"state-of-the-art":[143],"classifiers":[144],"around":[146],"3%":[147],"when":[148],"primary":[151],"considered":[154],"as":[155,191,205],"feature":[156,186],"generators.":[157],"show":[159],"that":[160],"situations":[161],"single-modality":[164],"may":[165],"be":[166],"confused":[167],"anomalous":[169],"points":[171],"now":[173],"corrected":[174],"through":[175],"emerging":[177],"integration.":[180],"Prominent":[181],"examples":[182,215],"include":[183],"water":[185],"city":[189],"misclassified":[190,204],"river":[193],"alone":[198],"densely":[201],"crowded":[202],"street":[203],"forest":[207],"alone.":[212],"Both":[213],"which":[216],"correctly":[218],"our":[221],"approach.":[223]},"counts_by_year":[],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}